© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13793
    Prev
    Next
    INDEX
    Explanations

    words related to media, music, especially singles or tracks

    oai_token-act-pair · gemini-2.0-flash

    single

    np_max-act · gemini-2.0-flash

    single Method used: 1 — matched common media-release tokens

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     autorytatywna
    -0.84
    expandindo
    -0.77
    ISupport
    -0.75
     مشين
    -0.70
     lenker
    -0.69
    новништво
    -0.69
    GraphicsUnit
    -0.68
    Flammability
    -0.68
     ***!
    -0.68
     useContext
    -0.66
    POSITIVE LOGITS
    <bos>
    0.64
    afone
    0.46
    .
    0.44
     ממש
    0.43
     Meksiku
    0.42
     Folge
    0.40
    婿
    0.40
    sivu
    0.39
    hoeddwyd
    0.39
     per
    0.39
    Activations Density 0.877%

    No Known Activations